Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    me provided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    1.06
    𝟬
    0.95
    ي
    0.93
    gh
    0.93
    γή
    0.92
    ি
    0.91
    ο
    0.89
     Mạnh
    0.88
    ी
    0.86
    יות
    0.86
    POSITIVE LOGITS
    ни
    1.16
    ların
    0.96
    fordshire
    0.93
     anot
    0.91
     eccentric
    0.91
    はこちら
    0.88
     errone
    0.86
     elucid
    0.84
    ين
    0.82
    ITHER
    0.79
    Act Density 0.094%

    No Known Activations